Detail publikace

QUALCOMM-ICSI-OGI Features for ASR

BURGET, L., DUPONT, S., GARUDADRI, H., GRÉZL, F., HEŘMANSKÝ, H., JAIN, P., KAJAREKAR, S., MORGAN, N.

Originální název

QUALCOMM-ICSI-OGI Features for ASR

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

Our feature extraction module for the Aurora task is based on a combination of a conventional noise supression technique (Wiener filtering) with our temporal processing technigues (linear discriminant RASTA filtering and nonlinear TempoRAl Pattern (TRAP) classifier). We observe better than 58% relative error improvement on the prescribed Aurora Digit Task, a performance level that is somewhat better than the new ETSI Advanced Feature standard. Furthermore, to test generalization of our approach to an independent test set not available during development, we evaluate performance on American English SpeechDatCar digits and show 10.54% relative improvement over the new ETSI standard.

Klíčová slova

feature extraction, distributed speech recognition, Aurora task, RASTA, TRAP

Autoři

BURGET, L., DUPONT, S., GARUDADRI, H., GRÉZL, F., HEŘMANSKÝ, H., JAIN, P., KAJAREKAR, S., MORGAN, N.

Rok RIV

2002

Vydáno

20. 9. 2002

Nakladatel

International Speech Communication Association

Místo

Denver

ISBN

1-876346-42-6

Kniha

Proc. 7th International Conference on Spoken Language Processing

Strany od

4

Strany do

7

Strany počet

4

URL

BibTex

@inproceedings{BUT10471,
  author="Lukáš {Burget} and Stephane {Dupont} and Harinath {Garudadri} and František {Grézl} and Hynek {Heřmanský} and Pratibha {Jain} and Sachin {Kajarekar} and Nelson {Morgan}",
  title="QUALCOMM-ICSI-OGI Features for ASR",
  booktitle="Proc. 7th International Conference on Spoken Language Processing",
  year="2002",
  pages="4",
  publisher="International Speech Communication Association",
  address="Denver",
  isbn="1-876346-42-6",
  url="http://www.fit.vutbr.cz/~burget/phd_activities/adami_icslp02.pdf"
}